{"id":"https://openalex.org/W4403277225","doi":"https://doi.org/10.1109/sbcci62366.2024.10703994","title":"Deep Nibble: A 4-bit Number Format for Efficient DNN Training and Inference in FPGA","display_name":"Deep Nibble: A 4-bit Number Format for Efficient DNN Training and Inference in FPGA","publication_year":2024,"publication_date":"2024-09-02","ids":{"openalex":"https://openalex.org/W4403277225","doi":"https://doi.org/10.1109/sbcci62366.2024.10703994"},"language":"en","primary_location":{"id":"doi:10.1109/sbcci62366.2024.10703994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbcci62366.2024.10703994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 37th SBC/SBMicro/IEEE Symposium on Integrated Circuits and Systems Design (SBCCI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013749383","display_name":"Luiz F. H. Duarte","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luiz F. H. Duarte","raw_affiliation_strings":["University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108183919","display_name":"George B. Nardes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"George B. Nardes","raw_affiliation_strings":["University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016727541","display_name":"Wesley Grignani","orcid":"https://orcid.org/0000-0003-4865-9333"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wesley Grignani","raw_affiliation_strings":["University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007786013","display_name":"Douglas R. Melo","orcid":"https://orcid.org/0000-0001-5791-6958"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Douglas R. Melo","raw_affiliation_strings":["University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063712781","display_name":"Cesar Albenes Zeferino","orcid":"https://orcid.org/0000-0003-3039-4410"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Cesar A. Zeferino","raw_affiliation_strings":["University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vale do Itajaí,Laboratory of Embedded and Distributed Systems,Brazil","institution_ids":["https://openalex.org/I4210144729"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144729"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27169382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13182","display_name":"Quantum-Dot Cellular Automata","score":0.9444000124931335,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13182","display_name":"Quantum-Dot Cellular Automata","score":0.9444000124931335,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9312999844551086,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367782592773438},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6426083445549011},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6024604439735413},{"id":"https://openalex.org/keywords/bit","display_name":"Bit (key)","score":0.5029515624046326},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48124122619628906},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42366665601730347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3978319466114044},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.33955830335617065},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13200396299362183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11520311236381531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367782592773438},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6426083445549011},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6024604439735413},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.5029515624046326},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48124122619628906},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42366665601730347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3978319466114044},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.33955830335617065},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13200396299362183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11520311236381531},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sbcci62366.2024.10703994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbcci62366.2024.10703994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 37th SBC/SBMicro/IEEE Symposium on Integrated Circuits and Systems Design (SBCCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.47999998927116394,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2999599167","https://openalex.org/W3063657173","https://openalex.org/W3089022192","https://openalex.org/W3100118801","https://openalex.org/W3165574855","https://openalex.org/W3177245350","https://openalex.org/W3208633927","https://openalex.org/W3211043030","https://openalex.org/W3216376605","https://openalex.org/W4285200511","https://openalex.org/W4285255298","https://openalex.org/W4312360312","https://openalex.org/W4313555487","https://openalex.org/W4327661768","https://openalex.org/W6696798448","https://openalex.org/W6753770798","https://openalex.org/W6785662278","https://openalex.org/W6810814891"],"related_works":["https://openalex.org/W2411923897","https://openalex.org/W4394546135","https://openalex.org/W4285347720","https://openalex.org/W4200259850","https://openalex.org/W2333831899","https://openalex.org/W2484894494","https://openalex.org/W2367385042","https://openalex.org/W2111241003","https://openalex.org/W4381186982","https://openalex.org/W2040781570"],"abstract_inverted_index":{"This":[0,52],"paper":[1],"introduces":[2],"a":[3,10,73],"compact":[4],"number":[5],"format":[6],"(Deep":[7,17],"Nibble)":[8],"and":[9,12,27,58,84,134,142],"resource-":[11],"performance-efficient":[13],"dot":[14],"product":[15],"core":[16,76],"Nibble":[18,101],"Unit":[19],"\u2013":[20],"DNU)":[21],"designed":[22,77],"to":[23,78,92,121],"address":[24],"the":[25,44,55,95,103,115,123,127,130,136],"performance":[26],"memory":[28,116],"bottlenecks":[29],"of":[30,82,87,105,126],"deep":[31,63,88],"learning":[32,89],"on":[33],"resource-constrained":[34],"devices.":[35],"Deep":[36,74,100],"Nibbles":[37],"are":[38],"4-bit":[39],"signal-exponent":[40],"numbers":[41],"generated":[42],"by":[43,118,140],"proposed":[45],"normalized":[46],"stochastic":[47],"logarithmic":[48],"quantization":[49],"(NSLQ)":[50],"method.":[51],"method":[53],"mitigates":[54],"gradient":[56],"vanishing":[57],"exploding":[59],"problems":[60],"in":[61],"training":[62,104],"neural":[64],"networks":[65],"(DNNs)":[66],"using":[67],"narrow":[68],"data":[69],"types.":[70],"DNU":[71,128],"is":[72],"Nibble-based":[75],"accelerate":[79],"MAC":[80,133],"operations":[81],"forward":[83],"backward":[85],"passes":[86],"systems.":[90],"Compared":[91,120],"FP32":[93],"formats,":[94],"experimental":[96],"results":[97],"show":[98],"that":[99],"supports":[102],"DNN":[106],"models":[107],"with":[108],"an":[109],"acceptable":[110],"accuracy":[111],"degradation":[112],"while":[113],"reducing":[114],"footprint":[117],"8\u00d7.":[119],"state-of-the-art,":[122],"FPGA":[124],"implementation":[125],"reduces":[129],"area":[131,139],"per":[132,138],"increases":[135],"throughput":[137],"3\u00d7":[141],"2.3\u00d7,":[143],"respectively.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}